© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116871
    Prev
    Next
    INDEX
    Explanations

    webpack loader

    np_acts-logits-general · gemini-2.5-flash-lite

    style urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Celebrating
    0.47
     पांडे
    0.46
     ጥላ
    0.46
    雔
    0.46
    桁
    0.46
    📃
    0.45
    クラス
    0.45
    蹉
    0.45
    版的
    0.45
    페이지
    0.44
    POSITIVE LOGITS
     th
    0.55
     Easy
    0.47
     femoral
    0.45
     soda
    0.45
     PBMCs
    0.45
     poch
    0.44
     Connection
    0.44
     fibr
    0.43
     EDTA
    0.42
     Pb
    0.42
    Activations Density 0.000%

    No Known Activations